ST

stabilityai japanese stablelm base gamma 7b

StabilityaiGGUF by RichardErkhovUpdated 2024-05-16
Download on Hugging Face
Parameters7.24B
Context4K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

stabilityai japanese stablelm base gamma 7b needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 2.7 GB (Q2_K) to 7.7 GB (Q8_0).

Japanese StableLM Base Gamma 7B – 7.24B parameter decoder‑only model

Japanese StableLM Base Gamma 7B is a 7.24B parameter decoder‑only language model. It focuses on Japanese language modeling and downstream tasks. The model is based on the llama architecture and was trained with Japanese data on top of an English model.

Good at

  • Japanese text generation
  • Japanese downstream tasks
  • Large context handling

Limits

  • No vision support
  • License not specified
  • No instruction‑following

Best for

  • Japanese content creation
  • Japanese NLP research
  • Japanese chatbot development

Who it’s for. Developers and researchers needing a Japanese‑focused language model. It is suitable for applications that require Japanese text generation and analysis.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 3.8 GB
Fits Get file →
IQ3_XS3.0 GB 4.1 GB
Fits Get file →
Q3_K_S3.2 GB 4.2 GB
Fits Get file →
IQ3_S3.2 GB 4.2 GB
Fits Get file →
IQ3_M3.3 GB 4.3 GB
Fits Get file →
Q3_K3.5 GB 4.6 GB
Fits Get file →
Q3_K_M3.5 GB 4.6 GB
Fits Get file →
Q3_K_L3.8 GB 4.9 GB
Fits Get file →
IQ4_XS3.9 GB 5.0 GB
Fits Get file →
Q4_04.1 GB 5.1 GB
Fits Get file →
Q4_K_S4.1 GB 5.2 GB
Fits Get file →
IQ4_NL4.2 GB 5.2 GB
Fits Get file →
Q4_K4.4 GB 5.4 GB
Fits Get file →
Q4_K_M4.4 GB 5.4 GB
Fits Get file →
Q4_14.6 GB 5.6 GB
Fits Get file →
Q5_05.0 GB 6.0 GB
Fits Get file →
Q5_K_S5.0 GB 6.0 GB
Fits Get file →
Q5_K5.1 GB 6.2 GB
Fits Get file →
Q5_K_M5.1 GB 6.2 GB
Fits Get file →
Q5_15.4 GB 6.5 GB
Fits Get file →
Q6_K5.9 GB 7.0 GB
Fits Get file →
Q8_07.7 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 4.11 GB, memory 5.7 GB). For 12 GB VRAM, Q5_0 (5 GB, 6.6 GB) or Q5_K (5.13 GB, 6.7 GB) are suitable. For 16 GB VRAM, Q6_K (5.94 GB, 7.5 GB) or Q8_0 (7.7 GB, 9.3 GB) can be used. Memory estimates are approximate.

What GPU do you need for stabilityai japanese stablelm base gamma 7b?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which stabilityai japanese stablelm base gamma 7b quant should you choose?

Q4_K_M is the usual starting point for stabilityai japanese stablelm base gamma 7b: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 2.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
Downloads (HF)2,692
Last updated2024-05-16

Frequently asked questions about stabilityai japanese stablelm base gamma 7b

How much VRAM does stabilityai japanese stablelm base gamma 7b need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run stabilityai japanese stablelm base gamma 7b on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stabilityai japanese stablelm base gamma 7b GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K is 3.5 GB and 16 more.

What context length does stabilityai japanese stablelm base gamma 7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download stabilityai japanese stablelm base gamma 7b GGUF?

The files are on Hugging Face in the RichardErkhov/stabilityai_-_japanese-stablelm-base-gamma-7b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q4_0 quantization uses 5.7 GB of VRAM at 8 k context, which fits within 8 GB.

Does this model support vision tasks?

No, it is a text‑only decoder‑only model with no vision capability.

What license applies to this model?

The model is licensed under Apache License, Version 2.0.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Stabilityai models

All Stabilityai →

Other small models

All small models →